Parallel Interactive Attention Network for Short-Term Origin–Destination Prediction in Urban Rail Transit
Short-term origin–destination (termed as OD) prediction is crucial to improve the operation of urban rail transit (termed as URT). The latest research results show that deep learning can effectively improve the performance of short-term OD prediction and meet the real-time requirements. However, man...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/1/100 |
| _version_ | 1797359178864394240 |
|---|---|
| author | Wenzhong Zhou Chunhai Gao Tao Tang |
| author_facet | Wenzhong Zhou Chunhai Gao Tao Tang |
| author_sort | Wenzhong Zhou |
| collection | DOAJ |
| description | Short-term origin–destination (termed as OD) prediction is crucial to improve the operation of urban rail transit (termed as URT). The latest research results show that deep learning can effectively improve the performance of short-term OD prediction and meet the real-time requirements. However, many advanced neural network design ideas have not been fully applied in the field of short-term OD prediction in URT. In this paper, a novel parallel interactive attention network (termed as PIANet) for short-term OD prediction in URT is proposed to further improve the short-term OD prediction accuracy. In the proposed PIANet, a novel omnidirectional attention module (termed as OAM) is proposed to improve the representational power of the network by calculating the feature weights in the channel–spatial dimension. Moreover, a simple yet effective feature interaction is proposed to improve the feature utilization. Based on the two real-world datasets from the Beijing subway, the comparative experiments demonstrate that the proposed PIANet outperforms the state-of-the-art deep learning methods for short-term OD prediction in URT, and the ablation studies demonstrate that the proposed OAMs and feature interaction play an important role in improving the short-term OD prediction accuracy. |
| first_indexed | 2024-03-08T15:12:54Z |
| format | Article |
| id | doaj.art-f6a424196ec740ccab30ede178ef4656 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T15:12:54Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f6a424196ec740ccab30ede178ef46562024-01-10T14:50:55ZengMDPI AGApplied Sciences2076-34172023-12-0114110010.3390/app14010100Parallel Interactive Attention Network for Short-Term Origin–Destination Prediction in Urban Rail TransitWenzhong Zhou0Chunhai Gao1Tao Tang2School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaTraffic Control Technology Co., Ltd., Beijing 100070, ChinaSchool of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaShort-term origin–destination (termed as OD) prediction is crucial to improve the operation of urban rail transit (termed as URT). The latest research results show that deep learning can effectively improve the performance of short-term OD prediction and meet the real-time requirements. However, many advanced neural network design ideas have not been fully applied in the field of short-term OD prediction in URT. In this paper, a novel parallel interactive attention network (termed as PIANet) for short-term OD prediction in URT is proposed to further improve the short-term OD prediction accuracy. In the proposed PIANet, a novel omnidirectional attention module (termed as OAM) is proposed to improve the representational power of the network by calculating the feature weights in the channel–spatial dimension. Moreover, a simple yet effective feature interaction is proposed to improve the feature utilization. Based on the two real-world datasets from the Beijing subway, the comparative experiments demonstrate that the proposed PIANet outperforms the state-of-the-art deep learning methods for short-term OD prediction in URT, and the ablation studies demonstrate that the proposed OAMs and feature interaction play an important role in improving the short-term OD prediction accuracy.https://www.mdpi.com/2076-3417/14/1/100origin–destination predictionurban rail transitdeep learningattention mechanism |
| spellingShingle | Wenzhong Zhou Chunhai Gao Tao Tang Parallel Interactive Attention Network for Short-Term Origin–Destination Prediction in Urban Rail Transit Applied Sciences origin–destination prediction urban rail transit deep learning attention mechanism |
| title | Parallel Interactive Attention Network for Short-Term Origin–Destination Prediction in Urban Rail Transit |
| title_full | Parallel Interactive Attention Network for Short-Term Origin–Destination Prediction in Urban Rail Transit |
| title_fullStr | Parallel Interactive Attention Network for Short-Term Origin–Destination Prediction in Urban Rail Transit |
| title_full_unstemmed | Parallel Interactive Attention Network for Short-Term Origin–Destination Prediction in Urban Rail Transit |
| title_short | Parallel Interactive Attention Network for Short-Term Origin–Destination Prediction in Urban Rail Transit |
| title_sort | parallel interactive attention network for short term origin destination prediction in urban rail transit |
| topic | origin–destination prediction urban rail transit deep learning attention mechanism |
| url | https://www.mdpi.com/2076-3417/14/1/100 |
| work_keys_str_mv | AT wenzhongzhou parallelinteractiveattentionnetworkforshorttermorigindestinationpredictioninurbanrailtransit AT chunhaigao parallelinteractiveattentionnetworkforshorttermorigindestinationpredictioninurbanrailtransit AT taotang parallelinteractiveattentionnetworkforshorttermorigindestinationpredictioninurbanrailtransit |